Quantification via Gaussian Latent Space Representations

TL;DR

This paper introduces a neural network approach using Gaussian latent space representations for quantification, achieving state-of-the-art results without relying on prior probability shift assumptions.

Contribution

The work presents a novel end-to-end deep learning method that directly optimizes quantification loss functions using Gaussian latent spaces, bypassing traditional classifier-based approaches.

Findings

Achieves state-of-the-art quantification accuracy

Outperforms traditional and deep learning methods

Provides publicly available code for reproducibility

Abstract

Quantification, or prevalence estimation, is the task of predicting the prevalence of each class within an unknown bag of examples. Most existing quantification methods in the literature rely on prior probability shift assumptions to create a quantification model that uses the predictions of an underlying classifier to make optimal prevalence estimates. In this work, we present an end-to-end neural network that uses Gaussian distributions in latent spaces to obtain invariant representations of bags of examples. This approach addresses the quantification problem using deep learning, enabling the optimization of specific loss functions relevant to the problem and avoiding the need for an intermediate classifier, tackling the quantification problem as a direct optimization problem. Our method achieves state-of-the-art results, both against traditional quantification methods and other deep learning approaches for quantification. The code needed to reproduce all our experiments is publicly available at https://github.com/AICGijon/gmnet.